KS
Killer-Skills

read-task — how to use read-task how to use read-task, read-task setup guide, read-task alternative, read-task vs Codex, collaborative development environment, tmux session management, Claude Code integration, Codex CLI tutorial, dual-agent development best practices

v1.0.0
GitHub

About this Skill

Ideal for Collaborative Agents like Claude Code that need to delegate tasks to other agents in a tmux session for efficient workflow management. read-task is a skill that facilitates collaborative development by pairing Claude Code with Codex CLI in a tmux session, enabling efficient task execution and delegation.

Features

Resolves the .agent-collab directory for seamless file operations
Utilizes bash commands for directory resolution and task execution
Supports collaborative development via tmux sessions
Pairs Claude Code with Codex CLI for efficient task delegation
Enables task execution outside the project root directory

# Core Topics

antorsae antorsae
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
36
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add antorsae/dual-agent/read-task

Agent Capability Analysis

The read-task MCP Server by antorsae is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use read-task, read-task setup guide, read-task alternative.

Ideal Agent Persona

Ideal for Collaborative Agents like Claude Code that need to delegate tasks to other agents in a tmux session for efficient workflow management.

Core Value

Empowers agents to execute tasks delegated from Claude Code, utilizing the `.agent-collab` directory for seamless collaboration and file operations, leveraging bash scripting for dynamic directory resolution and command execution.

Capabilities Granted for read-task MCP Server

Executing tasks from Claude Code in a collaborative environment
Managing dual-agent workflows with precision
Automating file operations within a tmux session

! Prerequisites & Limits

  • Requires access to the `.agent-collab` directory
  • Dependent on Claude Code for task delegation
  • Limited to bash-compatible environments
Project
SKILL.md
2.8 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Read Task Skill

Read and execute a task delegated from Claude Code.

Steps

Before any file operations, resolve the .agent-collab directory so commands work outside the project root:

bash
1AGENT_COLLAB_DIR="${AGENT_COLLAB_DIR:-}" 2if [ -n "$AGENT_COLLAB_DIR" ]; then 3 if [ -d "$AGENT_COLLAB_DIR/.agent-collab" ]; then 4 AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab" 5 elif [ ! -d "$AGENT_COLLAB_DIR" ]; then 6 AGENT_COLLAB_DIR="" 7 fi 8fi 9 10if [ -z "$AGENT_COLLAB_DIR" ]; then 11 AGENT_COLLAB_DIR="$(pwd)" 12 while [ "$AGENT_COLLAB_DIR" != "/" ] && [ ! -d "$AGENT_COLLAB_DIR/.agent-collab" ]; do 13 AGENT_COLLAB_DIR="$(dirname "$AGENT_COLLAB_DIR")" 14 done 15 AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab" 16fi

If $AGENT_COLLAB_DIR does not exist, stop and ask for the project root.

1. Update Status

Write working to $AGENT_COLLAB_DIR/status

2. Read the Task

Read $AGENT_COLLAB_DIR/requests/task.md and parse:

  • Task Type: CODE_REVIEW, IMPLEMENT, or PLAN_REVIEW
  • All requirements and context

3. Read Shared Context

Also read $AGENT_COLLAB_DIR/context/shared.md for project context.

4. Execute Based on Task Type

CODE_REVIEW

Perform thorough code review:

  • Analyze code line by line
  • Look for bugs, logic errors, edge cases
  • Check for security vulnerabilities
  • Identify performance problems
  • Check error handling
  • Suggest concrete improvements with code examples

Be thorough - take your time.

IMPLEMENT

Implement the requested feature:

  • Follow all requirements exactly
  • Match existing code patterns
  • Write clean, well-structured code
  • Handle edge cases and errors
  • Write code to specified target files

Take time for high-quality implementation.

PLAN_REVIEW

Critically analyze the plan:

  • Evaluate overall approach
  • Identify failure modes
  • Consider scalability/maintainability
  • Suggest alternatives if applicable
  • Point out missing considerations
  • Assess risks
  • Provide concrete recommendations

5. Write Response

Write complete response to $AGENT_COLLAB_DIR/responses/response.md:

markdown
1# Codex Response 2 3## Task Type 4[Task type handled] 5 6## Completed At 7[Timestamp] 8 9## Summary 10[Brief summary] 11 12## Detailed Findings/Output 13 14[For CODE_REVIEW:] 15### Critical Issues 16[List with severity] 17 18### Security Concerns 19[Security issues] 20 21### Suggestions 22[Improvements with examples] 23 24--- 25 26[For IMPLEMENT:] 27### Implementation Overview 28[What was implemented] 29 30### Files Created/Modified 31[List of files] 32 33### Integration Notes 34[How to integrate] 35 36--- 37 38[For PLAN_REVIEW:] 39### Overall Assessment 40[Is plan sound?] 41 42### Concerns 43[Issues identified] 44 45### Recommendations 46[Specific suggestions]

6. Update Status

Write done to $AGENT_COLLAB_DIR/status

7. Notify

Tell user response is ready and Claude can read it with /codex-read.

Related Skills

Looking for an alternative to read-task or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication